diff --git a/.env.example b/.env.example
index 44eb01b..578b618 100644
--- a/.env.example
+++ b/.env.example
@@ -31,12 +31,12 @@ REFRESH_INTERVAL_MINUTES=15
 
 # === LLM Layer (optional) ===
 # Enables AI-enhanced trade ideas and breaking news Telegram alerts.
-# Provider options: anthropic | openai | gemini | codex | openrouter | minimax
+# Provider options: anthropic | openai | gemini | codex | openrouter | minimax | mistral
 LLM_PROVIDER=
 # Not needed for codex (uses ~/.codex/auth.json)
 LLM_API_KEY=
 # Optional override. Each provider has a sensible default:
-# anthropic: claude-sonnet-4-6 | openai: gpt-5.4 | gemini: gemini-3.1-pro | codex: gpt-5.3-codex | openrouter: openrouter/auto | minimax: MiniMax-M2.5
+# anthropic: claude-sonnet-4-6 | openai: gpt-5.4 | gemini: gemini-3.1-pro | codex: gpt-5.3-codex | openrouter: openrouter/auto | minimax: MiniMax-M2.5 | mistral: mistral-small-latest
 LLM_MODEL=
 
 # === Telegram Alerts (optional, requires LLM) ===
diff --git a/README.md b/README.md
index 6bb7538..f4f7a73 100644
--- a/README.md
+++ b/README.md
@@ -158,10 +158,10 @@ Alerts are delivered as rich embeds with color-coded sidebars: red for FLASH, ye
 **Optional dependency:** The full bot requires `discord.js`. Install it with `npm install discord.js`. If it's not installed, Crucix automatically falls back to webhook-only mode.
 
 ### Optional LLM Layer
-Connect any of 6 LLM providers for enhanced analysis:
+Connect any of 7 LLM providers for enhanced analysis:
 - **AI trade ideas** — quantitative analyst producing 5-8 actionable ideas citing specific data
 - **Smarter alert evaluation** — LLM classifies signals into FLASH/PRIORITY/ROUTINE tiers with cross-domain correlation and confidence scoring
-- Providers: Anthropic Claude, OpenAI, Google Gemini, OpenRouter (Unified API), OpenAI Codex (ChatGPT subscription), MiniMax
+- Providers: Anthropic Claude, OpenAI, Google Gemini, OpenRouter (Unified API), OpenAI Codex (ChatGPT subscription), MiniMax, Mistral
 - Graceful fallback — when LLM is unavailable, a rule-based engine takes over alert evaluation. LLM failures never crash the sweep cycle.
 
 ---
@@ -194,7 +194,7 @@ These three unlock the most valuable economic and satellite data. Each takes abo
 
 ### LLM Provider (optional, for AI-enhanced ideas)
 
-Set `LLM_PROVIDER` to one of: `anthropic`, `openai`, `gemini`, `codex`, `openrouter`, `minimax`
+Set `LLM_PROVIDER` to one of: `anthropic`, `openai`, `gemini`, `codex`, `openrouter`, `minimax`, `mistral`
 
 | Provider | Key Required | Default Model |
 |----------|-------------|---------------|
@@ -204,6 +204,7 @@ Set `LLM_PROVIDER` to one of: `anthropic`, `openai`, `gemini`, `codex`, `openrou
 | `openrouter` | `LLM_API_KEY` | openrouter/auto |
 | `codex` | None (uses `~/.codex/auth.json`) | gpt-5.3-codex |
 | `minimax` | `LLM_API_KEY` | MiniMax-M2.5 |
+| `mistral` | `LLM_API_KEY` | mistral-small-latest |
 
 For Codex, run `npx @openai/codex login` to authenticate via your ChatGPT subscription.
 
@@ -273,7 +274,7 @@ crucix/
 │       └── jarvis.html        # Self-contained Jarvis HUD
 │
 ├── lib/
-│   ├── llm/                   # LLM abstraction (5 providers, raw fetch, no SDKs)
+│   ├── llm/                   # LLM abstraction (7 providers, raw fetch, no SDKs)
 │   │   ├── provider.mjs       # Base class
 │   │   ├── anthropic.mjs      # Claude
 │   │   ├── openai.mjs         # GPT
@@ -281,6 +282,7 @@ crucix/
 │   │   ├── openrouter.mjs     # OpenRouter (Unified API)
 │   │   ├── codex.mjs          # Codex (ChatGPT subscription)
 │   │   ├── minimax.mjs        # MiniMax (M2.5, 204K context)
+│   │   ├── mistral.mjs        # Mistral (OpenAI-compatible, JSON mode)
 │   │   ├── ideas.mjs          # LLM-powered trade idea generation
 │   │   └── index.mjs          # Factory: createLLMProvider()
 │   ├── delta/                 # Change tracking between sweeps
@@ -382,7 +384,7 @@ All settings are in `.env` with sensible defaults:
 |----------|---------|-------------|
 | `PORT` | `3117` | Dashboard server port |
 | `REFRESH_INTERVAL_MINUTES` | `15` | Auto-refresh interval |
-| `LLM_PROVIDER` | disabled | `anthropic`, `openai`, `gemini`, `codex`, `openrouter`, or `minimax` |
+| `LLM_PROVIDER` | disabled | `anthropic`, `openai`, `gemini`, `codex`, `openrouter`, `minimax`, or `mistral` |
 | `LLM_API_KEY` | — | API key (not needed for codex) |
 | `LLM_MODEL` | per-provider default | Override model selection |
 | `TELEGRAM_BOT_TOKEN` | disabled | For Telegram alerts + bot commands |
diff --git a/lib/llm/index.mjs b/lib/llm/index.mjs
index 7320a66..b2d16ee 100644
--- a/lib/llm/index.mjs
+++ b/lib/llm/index.mjs
@@ -6,6 +6,7 @@ import { OpenRouterProvider } from './openrouter.mjs';
 import { GeminiProvider } from './gemini.mjs';
 import { CodexProvider } from './codex.mjs';
 import { MiniMaxProvider } from './minimax.mjs';
+import { MistralProvider } from './mistral.mjs';
 
 export { LLMProvider } from './provider.mjs';
 export { AnthropicProvider } from './anthropic.mjs';
@@ -14,6 +15,7 @@ export { OpenRouterProvider } from './openrouter.mjs';
 export { GeminiProvider } from './gemini.mjs';
 export { CodexProvider } from './codex.mjs';
 export { MiniMaxProvider } from './minimax.mjs';
+export { MistralProvider } from './mistral.mjs';
 
 /**
  * Create an LLM provider based on config.
@@ -38,6 +40,8 @@ export function createLLMProvider(llmConfig) {
       return new CodexProvider({ model });
     case 'minimax':
       return new MiniMaxProvider({ apiKey, model });
+    case 'mistral':
+      return new MistralProvider({ apiKey, model });
     default:
       console.warn(`[LLM] Unknown provider "${provider}". LLM features disabled.`);
       return null;
diff --git a/lib/llm/mistral.mjs b/lib/llm/mistral.mjs
new file mode 100644
index 0000000..de6fefd
--- /dev/null
+++ b/lib/llm/mistral.mjs
@@ -0,0 +1,53 @@
+// Mistral Provider — raw fetch, no SDK
+// Uses Mistral's OpenAI-compatible Chat Completions API
+
+import { LLMProvider } from './provider.mjs';
+
+export class MistralProvider extends LLMProvider {
+  constructor(config) {
+    super(config);
+    this.name = 'mistral';
+    this.apiKey = config.apiKey;
+    this.model = config.model || 'mistral-small-latest';
+  }
+
+  get isConfigured() { return !!this.apiKey; }
+
+  async complete(systemPrompt, userMessage, opts = {}) {
+    const res = await fetch('https://api.mistral.ai/v1/chat/completions', {
+      method: 'POST',
+      headers: {
+        'Content-Type': 'application/json',
+        'Authorization': `Bearer ${this.apiKey}`,
+      },
+      body: JSON.stringify({
+        model: this.model,
+        max_tokens: opts.maxTokens || 4096,
+        messages: [
+          { role: 'system', content: systemPrompt },
+          { role: 'user', content: userMessage },
+        ],
+        // Enforce JSON output so callers can parse directly without markdown stripping
+        response_format: { type: 'json_object' },
+      }),
+      signal: AbortSignal.timeout(opts.timeout || 60000),
+    });
+
+    if (!res.ok) {
+      const err = await res.text().catch(() => '');
+      throw new Error(`Mistral API ${res.status}: ${err.substring(0, 200)}`);
+    }
+
+    const data = await res.json();
+    const text = data.choices?.[0]?.message?.content || '';
+
+    return {
+      text,
+      usage: {
+        inputTokens: data.usage?.prompt_tokens || 0,
+        outputTokens: data.usage?.completion_tokens || 0,
+      },
+      model: data.model || this.model,
+    };
+  }
+}
diff --git a/package.json b/package.json
index 5b90bf2..9972127 100644
--- a/package.json
+++ b/package.json
@@ -27,10 +27,13 @@
     "npm": ">=10"
   },
   "dependencies": {
+    "@mistralai/mistralai": "^2.0.0",
     "express": "^5.1.0"
   },
   "optionalDependencies": {
-    "discord.js": "^14.25.1"  },
+    "discord.js": "^14.25.1"
+  },
   "overrides": {
-    "undici": "^7.24.4"  }
+    "undici": "^7.24.4"
+  }
 }